SwinCNet leveraging Swin Transformer V2 and CNN for precise color correction and detail enhancement in underwater image restoration

Underwater image restoration confronts three major challenges: color distortion, contrast degradation, and detail blurring caused by light absorption and scattering. Current methods face difficulties in effectively balancing local detail preservation with global information integration. This study p...

Full description

Saved in:
Bibliographic Details
Main Authors: Chun Yang, Liwei Shao, Yi Deng, Jiahang Wang, Hexiang Zhai
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-03-01
Series:Frontiers in Marine Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fmars.2025.1523729/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849345166288093184
author Chun Yang
Liwei Shao
Yi Deng
Jiahang Wang
Hexiang Zhai
author_facet Chun Yang
Liwei Shao
Yi Deng
Jiahang Wang
Hexiang Zhai
author_sort Chun Yang
collection DOAJ
description Underwater image restoration confronts three major challenges: color distortion, contrast degradation, and detail blurring caused by light absorption and scattering. Current methods face difficulties in effectively balancing local detail preservation with global information integration. This study proposes SwinCNet, an innovative deep learning architecture that incorporates an enhanced Swin Transformer V2 following primary convolutional layers to achieve synergistic processing of local details and global dependencies. The architecture introduces two novel components: a dual-path feature extraction strategy and an adaptive feature fusion mechanism. These components work in tandem to preserve local structural information while strengthening cross-regional feature correlations during the encoding phase and enable precise multi-scale feature integration during decoding. Experimental results on the EUVP dataset demonstrate that SwinCNet achieves PSNR values of 24.1075 dB and 28.1944 dB on the EUVP-UI and EUVP-UD subsets, respectively. Furthermore, the model demonstrates competitive performance in reference-free evaluation metrics compared to existing methods while processing 512×512 resolution images in merely 30.32 ms—a significant efficiency improvement over conventional approaches, confirming its practical applicability in real-world underwater scenarios.
format Article
id doaj-art-e9c5ac25ca7d4d2e9804f786cbff38f1
institution Kabale University
issn 2296-7745
language English
publishDate 2025-03-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Marine Science
spelling doaj-art-e9c5ac25ca7d4d2e9804f786cbff38f12025-08-20T03:42:30ZengFrontiers Media S.A.Frontiers in Marine Science2296-77452025-03-011210.3389/fmars.2025.15237291523729SwinCNet leveraging Swin Transformer V2 and CNN for precise color correction and detail enhancement in underwater image restorationChun YangLiwei ShaoYi DengJiahang WangHexiang ZhaiUnderwater image restoration confronts three major challenges: color distortion, contrast degradation, and detail blurring caused by light absorption and scattering. Current methods face difficulties in effectively balancing local detail preservation with global information integration. This study proposes SwinCNet, an innovative deep learning architecture that incorporates an enhanced Swin Transformer V2 following primary convolutional layers to achieve synergistic processing of local details and global dependencies. The architecture introduces two novel components: a dual-path feature extraction strategy and an adaptive feature fusion mechanism. These components work in tandem to preserve local structural information while strengthening cross-regional feature correlations during the encoding phase and enable precise multi-scale feature integration during decoding. Experimental results on the EUVP dataset demonstrate that SwinCNet achieves PSNR values of 24.1075 dB and 28.1944 dB on the EUVP-UI and EUVP-UD subsets, respectively. Furthermore, the model demonstrates competitive performance in reference-free evaluation metrics compared to existing methods while processing 512×512 resolution images in merely 30.32 ms—a significant efficiency improvement over conventional approaches, confirming its practical applicability in real-world underwater scenarios.https://www.frontiersin.org/articles/10.3389/fmars.2025.1523729/fullSwin Transformer V2CNNunderwater image restorationprecise color correctiondeep learning
spellingShingle Chun Yang
Liwei Shao
Yi Deng
Jiahang Wang
Hexiang Zhai
SwinCNet leveraging Swin Transformer V2 and CNN for precise color correction and detail enhancement in underwater image restoration
Frontiers in Marine Science
Swin Transformer V2
CNN
underwater image restoration
precise color correction
deep learning
title SwinCNet leveraging Swin Transformer V2 and CNN for precise color correction and detail enhancement in underwater image restoration
title_full SwinCNet leveraging Swin Transformer V2 and CNN for precise color correction and detail enhancement in underwater image restoration
title_fullStr SwinCNet leveraging Swin Transformer V2 and CNN for precise color correction and detail enhancement in underwater image restoration
title_full_unstemmed SwinCNet leveraging Swin Transformer V2 and CNN for precise color correction and detail enhancement in underwater image restoration
title_short SwinCNet leveraging Swin Transformer V2 and CNN for precise color correction and detail enhancement in underwater image restoration
title_sort swincnet leveraging swin transformer v2 and cnn for precise color correction and detail enhancement in underwater image restoration
topic Swin Transformer V2
CNN
underwater image restoration
precise color correction
deep learning
url https://www.frontiersin.org/articles/10.3389/fmars.2025.1523729/full
work_keys_str_mv AT chunyang swincnetleveragingswintransformerv2andcnnforprecisecolorcorrectionanddetailenhancementinunderwaterimagerestoration
AT liweishao swincnetleveragingswintransformerv2andcnnforprecisecolorcorrectionanddetailenhancementinunderwaterimagerestoration
AT yideng swincnetleveragingswintransformerv2andcnnforprecisecolorcorrectionanddetailenhancementinunderwaterimagerestoration
AT jiahangwang swincnetleveragingswintransformerv2andcnnforprecisecolorcorrectionanddetailenhancementinunderwaterimagerestoration
AT hexiangzhai swincnetleveragingswintransformerv2andcnnforprecisecolorcorrectionanddetailenhancementinunderwaterimagerestoration